library(ggplot2)
library(akima)
library(dplyr)
##
## Attaching package: 'dplyr'
##
## The following objects are masked from 'package:stats':
##
## filter, lag
##
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyr)
library(reshape2)
library(car)
library(ade4)
library(adegraphics)
##
## Attaching package: 'adegraphics'
##
## The following objects are masked from 'package:ade4':
##
## kplotsepan.coa, s.arrow, s.class, s.corcircle, s.distri,
## s.image, s.label, s.logo, s.match, s.traject, s.value,
## table.value, triangle.class
afsp <- read.csv("~/afsp.csv")
afsp$wave <- as.factor(afsp$wave)
afsp$gndr <- as.factor(afsp$gndr)
afsp$i9r <- as.factor(afsp$i9r)
levels(afsp$gndr)[levels(afsp$gndr)=="1"] <- "Homme"
levels(afsp$gndr)[levels(afsp$gndr)=="2"] <- "Femme"
levels(afsp$i9r)[levels(afsp$i9r)=="0"] <- "Gauche"
levels(afsp$i9r)[levels(afsp$i9r)=="10"] <- "Droite"
afsp2 <- na.omit(afsp)
afsp2 <- filter(afsp2, wave=="1" | wave=="2" | wave=="4" | wave=="6" | wave=="7")
tab1 <- table(afsp2$i9r, afsp2$wave)
tab1.1 <- prop.table(tab1)
tab1.2 <- t(tab1.1)
tab1.3 <- prop.table(tab1,1)
tab2 <- addmargins(prop.table(tab1, 2),1)
tab2
##
## 1 2 3 4 5 6 7
## Gauche 0.00000000 0.00000000 0.01602564 0.03535354 0.06199021
## 1 0.04279601 0.04746318 0.03685897 0.03198653 0.02773246
## 2 0.03566334 0.03764321 0.07371795 0.08922559 0.07177814
## 3 0.12553495 0.11620295 0.11057692 0.09427609 0.11256117
## 4 0.11982882 0.11456628 0.12820513 0.08922559 0.09787928
## 5 0.10556348 0.09492635 0.23557692 0.22727273 0.23001631
## 6 0.24821683 0.26022913 0.09935897 0.10606061 0.10603589
## 7 0.10413695 0.10965630 0.12660256 0.12794613 0.11092985
## 8 0.10841655 0.11620295 0.12339744 0.12794613 0.10277325
## 9 0.08844508 0.08346972 0.02884615 0.03030303 0.03262643
## Droite 0.02139800 0.01963993 0.02083333 0.04040404 0.04567700
## Sum 1.00000000 1.00000000 1.00000000 1.00000000 1.00000000
dft2 <- as.data.frame.table(tab2)
d1 = as.data.frame(prop.table(table(afsp2$wave, afsp2$i9r),1)*100)
gg1 <- ggplot(d1, aes(x=Var1,y=Freq, fill=Var2))
gg1 + geom_bar(stat="identity") + xlab("vague d'enquête") + ylab("fréquence") + ggtitle("Evolution de l'autopositionnement")
## Warning: Removed 22 rows containing missing values (position_stack).
fmg <- lm(pgx ~ gndr + diplo+ religion+ age2 + i9r * wave, afsp2, weights=zpw)
summary(fmg)
##
## Call:
## lm(formula = pgx ~ gndr + diplo + religion + age2 + i9r * wave,
## data = afsp2, weights = zpw)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -11.4490 -0.6378 -0.0928 0.5861 9.0730
##
## Coefficients: (2 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 13.117082 1.611514 8.140 5.70e-16 ***
## gndrFemme -0.079508 0.056943 -1.396 0.162737
## diploaucun -2.214889 0.688500 -3.217 0.001309 **
## diploBAC -2.207513 0.687933 -3.209 0.001346 **
## diploBEPC -2.859362 0.686734 -4.164 3.22e-05 ***
## diploCAP / BEP -2.596845 0.685476 -3.788 0.000155 ***
## diploCEP -2.250437 0.699013 -3.219 0.001298 **
## diploUniv 1 -2.256670 0.687107 -3.284 0.001034 **
## diploUniv 2 -2.436291 0.687271 -3.545 0.000399 ***
## religionaucune -6.309289 1.322337 -4.771 1.92e-06 ***
## religionautre -6.206430 1.334723 -4.650 3.46e-06 ***
## religionchretiens -6.126780 1.321357 -4.637 3.69e-06 ***
## religionmusulman -5.225317 1.326852 -3.938 8.39e-05 ***
## age2 -0.018224 0.002158 -8.446 < 2e-16 ***
## i9r1 -0.045940 0.682811 -0.067 0.946363
## i9r2 0.599696 0.674283 0.889 0.373866
## i9r3 0.737954 0.636526 1.159 0.246405
## i9r4 -0.283756 0.637365 -0.445 0.656206
## i9r5 0.074642 0.643133 0.116 0.907613
## i9r6 -1.364271 0.621461 -2.195 0.028219 *
## i9r7 -1.998619 0.636730 -3.139 0.001712 **
## i9r8 -2.246275 0.639428 -3.513 0.000450 ***
## i9r9 -2.632260 0.647478 -4.065 4.91e-05 ***
## i9rDroite -2.840844 0.411117 -6.910 5.86e-12 ***
## wave2 -0.579930 0.646464 -0.897 0.369747
## wave4 -1.623191 0.723574 -2.243 0.024949 *
## wave6 -1.179439 0.667248 -1.768 0.077224 .
## wave7 0.089806 0.578445 0.155 0.876631
## i9r1:wave2 0.759688 0.770478 0.986 0.324213
## i9r2:wave2 0.701950 0.758213 0.926 0.354625
## i9r3:wave2 0.576030 0.698129 0.825 0.409376
## i9r4:wave2 0.215437 0.692395 0.311 0.755709
## i9r5:wave2 -0.518905 0.714085 -0.727 0.467483
## i9r6:wave2 -0.067772 0.665916 -0.102 0.918944
## i9r7:wave2 0.606470 0.693202 0.875 0.381707
## i9r8:wave2 0.440438 0.699295 0.630 0.528851
## i9r9:wave2 0.099208 0.729101 0.136 0.891776
## i9rDroite:wave2 NA NA NA NA
## i9r1:wave4 1.715160 0.878592 1.952 0.051009 .
## i9r2:wave4 1.348064 0.802794 1.679 0.093212 .
## i9r3:wave4 1.550839 0.765055 2.027 0.042739 *
## i9r4:wave4 1.443004 0.771570 1.870 0.061548 .
## i9r5:wave4 0.609220 0.760593 0.801 0.423205
## i9r6:wave4 1.190298 0.759765 1.567 0.117295
## i9r7:wave4 1.655087 0.760689 2.176 0.029648 *
## i9r8:wave4 1.318748 0.766305 1.721 0.085366 .
## i9r9:wave4 1.497774 0.863861 1.734 0.083051 .
## i9rDroite:wave4 1.144223 0.732851 1.561 0.118549
## i9r1:wave6 2.463474 0.858607 2.869 0.004144 **
## i9r2:wave6 1.236542 0.747333 1.655 0.098106 .
## i9r3:wave6 1.270710 0.729980 1.741 0.081828 .
## i9r4:wave6 0.673754 0.727759 0.926 0.354626
## i9r5:wave6 -0.051255 0.707143 -0.072 0.942223
## i9r6:wave6 0.883246 0.699730 1.262 0.206948
## i9r7:wave6 1.551520 0.718112 2.161 0.030807 *
## i9r8:wave6 0.803278 0.711653 1.129 0.259092
## i9r9:wave6 1.210684 0.813587 1.488 0.136832
## i9rDroite:wave6 0.829675 0.644841 1.287 0.198318
## i9r1:wave7 0.619958 0.775737 0.799 0.424244
## i9r2:wave7 -0.195389 0.681432 -0.287 0.774336
## i9r3:wave7 -0.891252 0.648302 -1.375 0.169309
## i9r4:wave7 0.030691 0.655334 0.047 0.962650
## i9r5:wave7 -1.565358 0.621241 -2.520 0.011795 *
## i9r6:wave7 -0.709118 0.617737 -1.148 0.251087
## i9r7:wave7 -0.201354 0.626091 -0.322 0.747774
## i9r8:wave7 -0.451384 0.643096 -0.702 0.482800
## i9r9:wave7 -0.320287 0.732320 -0.437 0.661882
## i9rDroite:wave7 NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.522 on 3077 degrees of freedom
## Multiple R-squared: 0.3928, Adjusted R-squared: 0.38
## F-statistic: 30.63 on 65 and 3077 DF, p-value: < 2.2e-16
fmd <- lm(pdx ~ gndr + diplo + religion + age2 + i9r * wave, afsp2, weights=zpw)
summary(fmd)
##
## Call:
## lm(formula = pdx ~ gndr + diplo + religion + age2 + i9r * wave,
## data = afsp2, weights = zpw)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -10.9256 -0.7413 0.0015 0.7352 12.1063
##
## Coefficients: (2 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.229618 1.726028 1.871 0.061422 .
## gndrFemme -0.403269 0.060990 -6.612 4.45e-11 ***
## diploaucun -1.472068 0.737425 -1.996 0.045997 *
## diploBAC -1.524373 0.736817 -2.069 0.038642 *
## diploBEPC -1.826946 0.735534 -2.484 0.013050 *
## diploCAP / BEP -2.192213 0.734186 -2.986 0.002850 **
## diploCEP -2.021892 0.748685 -2.701 0.006960 **
## diploUniv 1 -0.955134 0.735933 -1.298 0.194434
## diploUniv 2 -1.042325 0.736109 -1.416 0.156879
## religionaucune -0.336131 1.416302 -0.237 0.812416
## religionautre 0.052372 1.429569 0.037 0.970779
## religionchretiens 0.240730 1.415253 0.170 0.864945
## religionmusulman -0.011733 1.421138 -0.008 0.993413
## age2 0.006420 0.002311 2.778 0.005505 **
## i9r1 -1.088877 0.731332 -1.489 0.136617
## i9r2 -0.261809 0.722197 -0.363 0.716990
## i9r3 -0.307215 0.681757 -0.451 0.652294
## i9r4 0.186127 0.682656 0.273 0.785140
## i9r5 0.909661 0.688834 1.321 0.186739
## i9r6 0.926599 0.665622 1.392 0.163999
## i9r7 1.426951 0.681976 2.092 0.036487 *
## i9r8 1.791982 0.684866 2.617 0.008926 **
## i9r9 1.477322 0.693487 2.130 0.033228 *
## i9rDroite 1.681089 0.440331 3.818 0.000137 ***
## wave2 -0.122206 0.692402 -0.176 0.859916
## wave4 -1.071138 0.774991 -1.382 0.167032
## wave6 -0.498297 0.714663 -0.697 0.485701
## wave7 -0.165927 0.619550 -0.268 0.788857
## i9r1:wave2 0.290125 0.825228 0.352 0.725185
## i9r2:wave2 0.163984 0.812092 0.202 0.839986
## i9r3:wave2 0.455689 0.747738 0.609 0.542289
## i9r4:wave2 0.118032 0.741597 0.159 0.873553
## i9r5:wave2 -0.873676 0.764828 -1.142 0.253412
## i9r6:wave2 0.111329 0.713236 0.156 0.875972
## i9r7:wave2 0.189678 0.742461 0.255 0.798375
## i9r8:wave2 -0.220970 0.748987 -0.295 0.767995
## i9r9:wave2 0.621528 0.780911 0.796 0.426150
## i9rDroite:wave2 NA NA NA NA
## i9r1:wave4 1.480499 0.941025 1.573 0.115756
## i9r2:wave4 1.396585 0.859841 1.624 0.104428
## i9r3:wave4 1.447465 0.819420 1.766 0.077419 .
## i9r4:wave4 1.501848 0.826398 1.817 0.069262 .
## i9r5:wave4 1.482333 0.814640 1.820 0.068915 .
## i9r6:wave4 2.829346 0.813754 3.477 0.000514 ***
## i9r7:wave4 1.830346 0.814744 2.247 0.024741 *
## i9r8:wave4 1.595673 0.820759 1.944 0.051969 .
## i9r9:wave4 1.030133 0.925248 1.113 0.265641
## i9rDroite:wave4 -0.064574 0.784928 -0.082 0.934439
## i9r1:wave6 0.945910 0.919620 1.029 0.303755
## i9r2:wave6 1.019861 0.800439 1.274 0.202715
## i9r3:wave6 1.088105 0.781852 1.392 0.164114
## i9r4:wave6 1.433357 0.779474 1.839 0.066029 .
## i9r5:wave6 1.176746 0.757392 1.554 0.120363
## i9r6:wave6 1.481761 0.749452 1.977 0.048117 *
## i9r7:wave6 1.684686 0.769141 2.190 0.028574 *
## i9r8:wave6 1.052980 0.762224 1.381 0.167239
## i9r9:wave6 2.195915 0.871401 2.520 0.011786 *
## i9rDroite:wave6 -0.497850 0.690663 -0.721 0.471070
## i9r1:wave7 0.566886 0.830861 0.682 0.495109
## i9r2:wave7 0.589948 0.729855 0.808 0.418976
## i9r3:wave7 0.871696 0.694370 1.255 0.209438
## i9r4:wave7 0.975766 0.701902 1.390 0.164577
## i9r5:wave7 0.440600 0.665387 0.662 0.507911
## i9r6:wave7 2.200933 0.661634 3.327 0.000890 ***
## i9r7:wave7 1.558613 0.670581 2.324 0.020176 *
## i9r8:wave7 0.765796 0.688794 1.112 0.266315
## i9r9:wave7 0.727346 0.784359 0.927 0.353837
## i9rDroite:wave7 NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.631 on 3077 degrees of freedom
## Multiple R-squared: 0.3517, Adjusted R-squared: 0.338
## F-statistic: 25.68 on 65 and 3077 DF, p-value: < 2.2e-16
fmfn <- lm(fn ~ gndr + diplo + religion + age2 + i9r * wave, afsp2, weights=zpw)
summary(fmfn)
##
## Call:
## lm(formula = fn ~ gndr + diplo + religion + age2 + i9r * wave,
## data = afsp2, weights = zpw)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -15.0000 -1.2244 -0.1278 0.8175 21.0372
##
## Coefficients: (2 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.483934 2.928690 -0.165 0.86877
## gndrFemme -0.030008 0.103486 -0.290 0.77186
## diploaucun -1.791785 1.251247 -1.432 0.15225
## diploBAC -3.142487 1.250217 -2.514 0.01200 *
## diploBEPC -2.957773 1.248039 -2.370 0.01785 *
## diploCAP / BEP -1.806102 1.245753 -1.450 0.14721
## diploCEP -3.034511 1.270354 -2.389 0.01697 *
## diploUniv 1 -3.428938 1.248716 -2.746 0.00607 **
## diploUniv 2 -3.943438 1.249014 -3.157 0.00161 **
## religionaucune 3.478450 2.403153 1.447 0.14787
## religionautre 2.310874 2.425664 0.953 0.34083
## religionchretiens 3.148468 2.401372 1.311 0.18992
## religionmusulman 2.942613 2.411359 1.220 0.22244
## age2 -0.008650 0.003921 -2.206 0.02748 *
## i9r1 1.244252 1.240909 1.003 0.31609
## i9r2 0.809193 1.225410 0.660 0.50908
## i9r3 1.188667 1.156792 1.028 0.30424
## i9r4 0.959308 1.158318 0.828 0.40763
## i9r5 2.707298 1.168800 2.316 0.02061 *
## i9r6 3.489506 1.129414 3.090 0.00202 **
## i9r7 2.909425 1.157164 2.514 0.01198 *
## i9r8 3.237606 1.162067 2.786 0.00537 **
## i9r9 6.846491 1.176696 5.818 6.55e-09 ***
## i9rDroite 6.981672 0.747145 9.344 < 2e-16 ***
## wave2 -1.257119 1.174854 -1.070 0.28469
## wave4 1.701881 1.314989 1.294 0.19569
## wave6 0.128909 1.212626 0.106 0.91535
## wave7 1.293610 1.051240 1.231 0.21858
## i9r1:wave2 0.943793 1.400231 0.674 0.50034
## i9r2:wave2 1.477205 1.377941 1.072 0.28379
## i9r3:wave2 1.336778 1.268746 1.054 0.29214
## i9r4:wave2 1.299766 1.258327 1.033 0.30172
## i9r5:wave2 2.407347 1.297745 1.855 0.06369 .
## i9r6:wave2 0.646359 1.210204 0.534 0.59332
## i9r7:wave2 0.227305 1.259793 0.180 0.85683
## i9r8:wave2 1.053451 1.270865 0.829 0.40721
## i9r9:wave2 -0.285103 1.325033 -0.215 0.82965
## i9rDroite:wave2 NA NA NA NA
## i9r1:wave4 -2.650965 1.596712 -1.660 0.09696 .
## i9r2:wave4 -1.319684 1.458961 -0.905 0.36578
## i9r3:wave4 -2.280640 1.390375 -1.640 0.10104
## i9r4:wave4 -0.165036 1.402216 -0.118 0.90632
## i9r5:wave4 -1.600475 1.382265 -1.158 0.24701
## i9r6:wave4 -1.180327 1.380761 -0.855 0.39271
## i9r7:wave4 -0.652358 1.382441 -0.472 0.63704
## i9r8:wave4 -0.043355 1.392647 -0.031 0.97517
## i9r9:wave4 -0.305225 1.569941 -0.194 0.84586
## i9rDroite:wave4 -5.802640 1.331850 -4.357 1.36e-05 ***
## i9r1:wave6 -0.205756 1.560393 -0.132 0.89510
## i9r2:wave6 -0.236980 1.358168 -0.174 0.86150
## i9r3:wave6 -0.839653 1.326632 -0.633 0.52683
## i9r4:wave6 0.486443 1.322595 0.368 0.71305
## i9r5:wave6 0.757983 1.285128 0.590 0.55536
## i9r6:wave6 -0.729493 1.271656 -0.574 0.56624
## i9r7:wave6 1.864205 1.305063 1.428 0.15327
## i9r8:wave6 0.575135 1.293326 0.445 0.65657
## i9r9:wave6 -1.350885 1.478576 -0.914 0.36098
## i9rDroite:wave6 2.346929 1.171904 2.003 0.04530 *
## i9r1:wave7 -1.931249 1.409789 -1.370 0.17082
## i9r2:wave7 -1.037266 1.238403 -0.838 0.40233
## i9r3:wave7 -1.178985 1.178193 -1.001 0.31706
## i9r4:wave7 -0.235620 1.190973 -0.198 0.84318
## i9r5:wave7 -1.363885 1.129015 -1.208 0.22713
## i9r6:wave7 -1.675980 1.122647 -1.493 0.13557
## i9r7:wave7 -0.304736 1.137828 -0.268 0.78885
## i9r8:wave7 0.614364 1.168732 0.526 0.59916
## i9r9:wave7 -4.259625 1.330884 -3.201 0.00139 **
## i9rDroite:wave7 NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.767 on 3077 degrees of freedom
## Multiple R-squared: 0.2872, Adjusted R-squared: 0.2722
## F-statistic: 19.08 on 65 and 3077 DF, p-value: < 2.2e-16
fmx <- lm(pgx ~ fn*pdx* wave, afsp2, weights=zpw)
summary(fmx)
##
## Call:
## lm(formula = pgx ~ fn * pdx * wave, data = afsp2, weights = zpw)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -9.6253 -0.9406 -0.0810 0.8187 12.0437
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.9080026 0.1431545 20.314 < 2e-16 ***
## fn -0.2038448 0.0384589 -5.300 1.24e-07 ***
## pdx 0.0375410 0.0499373 0.752 0.4523
## wave2 -0.3446162 0.2010421 -1.714 0.0866 .
## wave4 0.2278505 0.2058959 1.107 0.2685
## wave6 0.0629909 0.2205794 0.286 0.7752
## wave7 -0.0056673 0.2127917 -0.027 0.9788
## fn:pdx 0.0189464 0.0119264 1.589 0.1123
## fn:wave2 -0.0285682 0.0572331 -0.499 0.6177
## fn:wave4 -0.0007342 0.0567684 -0.013 0.9897
## fn:wave6 -0.0758560 0.0576764 -1.315 0.1885
## fn:wave7 0.0140225 0.0564737 0.248 0.8039
## pdx:wave2 -0.0411135 0.0687859 -0.598 0.5501
## pdx:wave4 -0.1179146 0.0678668 -1.737 0.0824 .
## pdx:wave6 -0.0999753 0.0695119 -1.438 0.1505
## pdx:wave7 -0.0989410 0.0683039 -1.449 0.1476
## fn:pdx:wave2 0.0179174 0.0181678 0.986 0.3241
## fn:pdx:wave4 -0.0033724 0.0159792 -0.211 0.8329
## fn:pdx:wave6 0.0244206 0.0170622 1.431 0.1525
## fn:pdx:wave7 -0.0034356 0.0157293 -0.218 0.8271
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.865 on 3123 degrees of freedom
## Multiple R-squared: 0.07504, Adjusted R-squared: 0.06941
## F-statistic: 13.33 on 19 and 3123 DF, p-value: < 2.2e-16
ak2 <- read.csv("~/ak2.csv")
ak2 <- na.omit(ak2)
aki.2 <- interp(ak2$pgx, ak2$pdx, ak2$fn,
xo=seq(min(ak2$pgx), max(ak2$pgx), length = 20),
yo=seq(min(ak2$pdx), max(ak2$pdx), length = 20), duplicate="median")
filled.contour(x = aki.2$x,
y = aki.2$y,
z = aki.2$z,
color.palette =
colorRampPalette(c("white", "red")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique 2014",
key.title = title(main = "FN", cex.main = 1))
ak21 <- filter(ak2, wave==1)
ak22 <- filter(ak2, wave==2)
ak24 <- filter(ak2, wave==4)
ak26 <- filter(ak2, wave==6)
ak27 <- filter(ak2, wave==7)
akima.li <- interp(ak21$pgx, ak21$pdx, ak21$fn,
xo=seq(min(ak21$pgx), max(ak21$pgx), length = 100),
yo=seq(min(ak21$pdx), max(ak21$pdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "black")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique 2014 - vague 1",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak22$pgx, ak22$pdx, ak22$fn,
xo=seq(min(ak22$pgx), max(ak22$pgx), length = 100),
yo=seq(min(ak22$pdx), max(ak22$pdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "black")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique 2014 - vague 2",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak24$pgx, ak24$pdx, ak24$fn,
xo=seq(min(ak24$pgx), max(ak24$pgx), length = 100),
yo=seq(min(ak24$pdx), max(ak24$pdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "black")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique 2014 - vague 4",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak26$pgx, ak26$pdx, ak26$fn,
xo=seq(min(ak26$pgx), max(ak26$pgx), length = 100),
yo=seq(min(ak26$pdx), max(ak26$pdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "black")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique 2014 - vague 6",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak27$pgx, ak27$pdx, ak27$fn,
xo=seq(min(ak27$pgx), max(ak27$pgx), length = 100),
yo=seq(min(ak27$pdx), max(ak27$pdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "black")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique 2014 - vague 7",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak2$pgx, ak2$pdx, ak2$fn,
xo=seq(min(ak2$pgx), max(ak2$pgx), length = 100),
yo=seq(min(ak2$pdx), max(ak2$pdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "blue")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique synthétique",
key.title = title(main = "FN", cex.main = 1))
ak3 <- read.csv("~/ak3.csv")
ak3 <- na.omit(ak3)
akima.li <- interp(ak3$ypgx, ak3$ypdx, ak3$yfnx,
xo=seq(min(ak3$ypgx), max(ak3$ypgx), length = 100),
yo=seq(min(ak3$ypdx), max(ak3$ypdx), length = 100), duplicate="median")
ak31 <- filter(ak3, wave==1)
ak32 <- filter(ak3, wave==2)
ak34 <- filter(ak3, wave==4)
ak36 <- filter(ak3, wave==6)
ak37 <- filter(ak3, wave==7)
akima.li <- interp(ak31$ypgx, ak31$ypdx, ak31$yfnx,
xo=seq(min(ak31$ypgx), max(ak31$ypgx), length = 100),
yo=seq(min(ak31$ypdx), max(ak31$ypdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "blue")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique - vague 1",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak32$ypgx, ak32$ypdx, ak32$yfnx,
xo=seq(min(ak32$ypgx), max(ak32$ypgx), length = 100),
yo=seq(min(ak32$ypdx), max(ak32$ypdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "blue")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique - vague 2",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak34$ypgx, ak34$ypdx, ak34$yfnx,
xo=seq(min(ak34$ypgx), max(ak34$ypgx), length = 100),
yo=seq(min(ak34$ypdx), max(ak34$ypdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "blue")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique - vague 4",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak36$ypgx, ak36$ypdx, ak36$yfnx,
xo=seq(min(ak36$ypgx), max(ak36$ypgx), length = 100),
yo=seq(min(ak36$ypdx), max(ak36$ypdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "blue")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique - vague 6",
key.title = title(main = "FN", cex.main = 1))
akima.li <- interp(ak37$ypgx, ak37$ypdx, ak37$yfnx,
xo=seq(min(ak37$ypgx), max(ak37$ypgx), length = 100),
yo=seq(min(ak37$ypdx), max(ak37$ypdx), length = 100), duplicate="median")
filled.contour(x = akima.li$x,
y = akima.li$y,
z = akima.li$z,
color.palette =
colorRampPalette(c("white", "blue")),
xlab = "gauche",
ylab = "droite",
main = "Espace politique - vague 7",
key.title = title(main = "FN", cex.main = 1))
p <- ggplot(ak3, aes(ypgx, ypdx))
p + geom_point(aes(colour=yfnx,size=yfnx)) + scale_colour_gradient( low="white", high="darkblue")
p + geom_point(aes(colour=yfnx,size=yfnx)) + scale_colour_gradient( low="white", high="darkblue") + facet_wrap(~wave, ncol=4)
dat2 <- read.csv("~/Desktop/dat2.csv")
head(dat2)
## UID_DYNA wave id lo npa pcf pg ps prg vec mod udi ump dlr fn pgx
## 1 1 2 1_2 0 0 0 0 5 0 0 3 9 7 0 0 0.7142857
## 2 1 1 1_1 0 0 0 0 2 0 0 3 0 10 0 0 0.2857143
## 3 1 4 1_4 0 0 0 0 2 0 2 4 3 7 2 0 0.5714286
## 4 1 6 1_6 0 0 0 0 2 0 2 4 3 8 3 0 0.5714286
## 5 1 7 1_7 0 0 0 0 5 3 0 0 6 7 4 0 1.1428571
## 6 2 4 2_4 0 1 1 1 4 3 1 5 3 2 2 0 1.5714286
## pdx i9r
## 1 4.75 8
## 2 3.25 8
## 3 4.00 7
## 4 4.50 8
## 5 4.25 8
## 6 3.00 4
colnames(dat2)
## [1] "UID_DYNA" "wave" "id" "lo" "npa" "pcf"
## [7] "pg" "ps" "prg" "vec" "mod" "udi"
## [13] "ump" "dlr" "fn" "pgx" "pdx" "i9r"
dat2 <- dat2[order(dat2$UID_DYNA, dat2$wave),]
s1 <- select(dat2, pgx, pdx)
s2 <- select(dat2, i9r)
s2$i9r <- as.factor(s2$i9r)
s.class(s1, s2$i9r, col = rainbow(11))
s1.1 <- select(dat2, ps, ump)
s.class(s1.1, s2$i9r, col = rainbow(11))
s1.2 <- select(dat2, ps, fn)
s.class(s1.2, s2$i9r, col = rainbow(11))
s1.3<- select(dat2, ump, fn)
s.class(s1.3, s2$i9r, col = rainbow(11))
d2w1 <- filter(dat2, wave==1)
d2w2 <- filter(dat2, wave==2)
d2w4 <- filter(dat2, wave==4)
d2w6 <- filter(dat2, wave==6)
d2w7 <- filter(dat2, wave==7)
d2w1.1 <- select(d2w1, lo:fn)
d2w2.1 <- select(d2w2, lo:fn)
d2w4.1 <- select(d2w4, lo:fn)
d2w6.1 <- select(d2w6, lo:fn)
d2w7.1 <- select(d2w7, lo:fn)
w1.dudic <- dudi.pca(d2w1.1, scannf= FALSE, center=TRUE)
w2.dudic <- dudi.pca(d2w2.1, scannf= FALSE, center=TRUE)
w4.dudic <- dudi.pca(d2w4.1, scannf= FALSE, center=TRUE)
w6.dudic <- dudi.pca(d2w6.1, scannf= FALSE, center=TRUE)
w7.dudic <- dudi.pca(d2w7.1, scannf= FALSE, center=TRUE)
kta2 <- ktab.list.dudi(list(w1.dudic, w2.dudic, w4.dudic, w6.dudic, w7.dudic),tabnames = c("1", "2", "4", "6", "7"))
atp2 <- pta(kta2, scannf=FALSE, nf=2)
summary(atp2)
## Class: pta dudi
## Call: pta(X = kta2, scannf = FALSE, nf = 2)
##
## Total inertia: 46.25
##
## Eigenvalues:
## Ax1 Ax2 Ax3 Ax4 Ax5
## 18.687 8.401 7.323 2.445 2.073
##
## Projected inertia (%):
## Ax1 Ax2 Ax3 Ax4 Ax5
## 40.406 18.166 15.835 5.288 4.482
##
## Cumulative projected inertia (%):
## Ax1 Ax1:2 Ax1:3 Ax1:4 Ax1:5
## 40.41 58.57 74.41 79.69 84.18
##
## (Only 5 dimensions (out of 12) are shown)
plot(atp2)
fTli <- atp2$Tli
block <- rep(1:488, 5)
b2 <- as.factor(block)
s.class(fTli, b2)
afm <- mfa(kta2, scannf=FALSE, nf=2)
summary(afm)
## Multiple Factorial Analysis
## rows: 488 columns: 60
##
## $eig: 60 eigen values
## 4.358 1.962 1.714 0.5786 0.4947 ...
plot(afm)
kplot(afm)
afm2 <- afm$lisup
s.class(afm2, b2)
s.traject(afm2, b2, plab.cex=0, ppoints.cex=0.2)
s.traject(afm2, b2, col=cm.colors(500), plab.cex=0, ppoints.cex=0.2)
s.traject(afm2, b2, col=heat.colors(500), plab.cex=0, ppoints.cex=0.2)
s.traject(afm2, b2, col=terrain.colors(500), plab.cex=0, ppoints.cex=0.2)
s.traject(afm2, b2, col=topo.colors(500), plab.cex=0, ppoints.cex=0.2)
gx <- cbind(afm2, dat2)
head(gx)
## Fac1 Fac2 UID_DYNA wave id lo npa pcf pg ps prg vec mod
## 1.1 1.0947711 0.27083860 1 1 1_1 0 0 0 0 2 0 0 3
## 2.1 -0.3886392 0.58487751 1 2 1_2 0 0 0 0 5 0 0 3
## 3.1 0.9763921 -0.20703497 1 4 1_4 0 0 0 0 2 0 2 4
## 4.1 0.8762126 -0.09149023 1 6 1_6 0 0 0 0 2 0 2 4
## 5.1 0.1547022 0.52334334 1 7 1_7 0 0 0 0 5 3 0 0
## 6.1 -0.8087353 -0.73540091 2 1 2_1 4 2 2 3 5 1 3 0
## udi ump dlr fn pgx pdx i9r
## 1.1 0 10 0 0 0.2857143 3.25 8
## 2.1 9 7 0 0 0.7142857 4.75 8
## 3.1 3 7 2 0 0.5714286 4.00 7
## 4.1 3 8 3 0 0.5714286 4.50 8
## 5.1 6 7 4 0 1.1428571 4.25 8
## 6.1 0 0 0 3 2.8571429 0.00 4
p <- ggplot(gx, aes(Fac1, Fac2))
p + geom_path(aes(colour=i9r))
p + geom_path(aes(colour=wave))
p + geom_path(aes(colour=wave)) + facet_wrap(~UID_DYNA)
p + geom_path(aes(colour=wave)) + facet_wrap(~i9r)
p + geom_path(aes(colour=wave)) + facet_wrap(~lo)
p + geom_path(aes(colour=wave)) + facet_wrap(~fn)
